Creating and Integrating a Google Dialogflow Chatbot with a React Native Frontend
Cortez, Charles (2025)
2025
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2025051210746
https://urn.fi/URN:NBN:fi:amk-2025051210746
Tiivistelmä
The objective of this project was to develop and integrate a chatbot using Google Dialogflow as the foundation and React Native as the frontend framework, enhancing accessibility to peer-to-peer and professional support for new parents.
The chatbot was implemented into the Hello There Oy mobile application using React Native, allowing cross-platform compatibility for both Android and iOS devices. Google Dialogflow was used to manage conversational logic, intent recognition, and entity extraction. For backend operations, Google Cloud Functions facilitated secure and scalable connections between the chatbot and Google Cloud SQL database application. Cloud Functions processed user input and dynamically retrieved relevant data from the SQL database as needed.
The chatbot acted as an intelligent intermediary between users and the available support options. By analyzing users' input in real time, it identified their needs and matched them with the most relevant peer or professional support. This automated matching process significantly reduced the time required for users to find appropriate help. Additionally, by incorporating real-time responses and a ranking mechanism to prioritize support options, the system improved both user engagement and overall efficiency.
The implementation demonstrated the potential of AI-driven solutions in streamlining support services, with future improvements aimed at enhancing chatbot functionality and refining NLP accuracy.
The chatbot was implemented into the Hello There Oy mobile application using React Native, allowing cross-platform compatibility for both Android and iOS devices. Google Dialogflow was used to manage conversational logic, intent recognition, and entity extraction. For backend operations, Google Cloud Functions facilitated secure and scalable connections between the chatbot and Google Cloud SQL database application. Cloud Functions processed user input and dynamically retrieved relevant data from the SQL database as needed.
The chatbot acted as an intelligent intermediary between users and the available support options. By analyzing users' input in real time, it identified their needs and matched them with the most relevant peer or professional support. This automated matching process significantly reduced the time required for users to find appropriate help. Additionally, by incorporating real-time responses and a ranking mechanism to prioritize support options, the system improved both user engagement and overall efficiency.
The implementation demonstrated the potential of AI-driven solutions in streamlining support services, with future improvements aimed at enhancing chatbot functionality and refining NLP accuracy.